Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1754 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1154. Min Act: -0.0000

Data Index: 452007 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0799. Min Act: -0.0000

Data Index: 643823 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1230. Min Act: -0.0000

Data Index: 490347 (C4 (Web Text))

Max Activating Token Index: 806

Text #3

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0807. Min Act: -0.0000

Data Index: 330600 (C4 (Web Text))

Max Activating Token Index: 995

Text #4

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0796. Min Act: -0.0000

Data Index: 4160 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0819. Min Act: -0.0000

Data Index: 783567 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0801. Min Act: -0.0000

Data Index: 625163 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0593. Min Act: -0.0000

Data Index: 338737 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0687. Min Act: -0.0000

Data Index: 1248487 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0641. Min Act: -0.0000

Data Index: 414259 (C4 (Web Text))

Max Activating Token Index: 618

Text #10

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0711. Min Act: -0.0000

Data Index: 1499197 (Python Code)

Max Activating Token Index: 438

Text #11

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0519. Min Act: -0.0000

Data Index: 1186220 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0707. Min Act: -0.0000

Data Index: 463372 (C4 (Web Text))

Max Activating Token Index: 762

Text #13

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0651. Min Act: -0.0000

Data Index: 125536 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1157. Min Act: -0.0000

Data Index: 118577 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0574. Min Act: -0.0000

Data Index: 250919 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0632. Min Act: -0.0000

Data Index: 1161682 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0653. Min Act: -0.0000

Data Index: 636371 (C4 (Web Text))

Max Activating Token Index: 832

Text #18

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0620. Min Act: -0.0000

Data Index: 1033866 (C4 (Web Text))

Max Activating Token Index: 821

Text #19

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0619. Min Act: -0.0000

Data Index: 853227 (C4 (Web Text))

Max Activating Token Index: 669